Skip to content

Repository files navigation

SoundScribe

SoundScribe is an innovative AI-driven transcription tool designed to convert audio files into text using cutting-edge technologies. This tool harnesses the power of Whisper AI alongside Node.js to provide accurate and efficient transcription services for various industries.

Features

  • File Compatibility: Supports .mp4, .m4a, and .mp3 audio file formats.
  • Output Formats: Generates transcripts in .txt, .srt, and .json formats.
  • AI-Powered Transcription: Leverages Whisper AI's advanced capabilities for speech recognition and transcription.
  • Seamless Integration: Node.js framework allows for smooth application management and integration.
  • High Precision and Speed: Provides fast and precise conversion of audio to text.

Usage

Requirements

To use SoundScribe, ensure the following:

  • Node.js installed
  • Python 3.10
  • Whisper AI library
  • Minimum 8 GB VRAM: SoundScribe requires a system with a minimum of 8 GB VRAM to perform efficiently due to the computational demands of Whisper AI's advanced features.

Installation

Docker Container Installation

  1. Pull the Docker Image:

    docker pull yourusername/soundscribe:latest
  2. Run the Docker Container:

    docker run -it -d yourusername/soundscribe:latest

Local Setup

  1. Clone the Repository:

    git clone https://github.com/yourusername/SoundScribe.git
    cd SoundScribe
  2. Install Dependencies:

    # Command to install Node.js dependencies
    npm install
    # Command to set up Whisper AI environment (refer to Whisper AI's setup documentation)
  3. Start the Application:

    # Command to start SoundScribe
    # Add necessary command or scripts here

Note: For local setup, ensure your system meets the minimum requirements, including Node.js and a minimum of 8 GB VRAM for optimal performance.

Choose the installation method that best suits your needs. The Docker container option provides a streamlined setup, while the local setup allows for more control and customization of the environment.

Clone the repository:

https://github.com/addynoven/SoundScribe.git

About

"SoundScribe, an AI-driven transcription tool, combines Node.js and Python TensorFlow to transcribe audio accurately. This fusion offers high-precision, fast conversion of audio to text, serving diverse industries' transcription needs."

Resources

Stars

1 star

Watchers

1 watching

Forks

Releases

Packages

Used by

Contributors

Languages